GPT-4o
openai/gpt-4o
Compare with GPT-4o-mini, GPT-4, GPT-4o (2024-05-13)
CompareGPT-4o
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Azureazure | Healthy | 100% | 99.94% | 833ms | 4.46s | 3.0 tps | 128K | $2.50 / $10.00 |
OpenAIopenai | Healthy | 99.98% | 99.94% | 634ms | 5.47s | 40 tps | 128K | $2.50 / $10.00 |
- Azure100%Healthy24h 99.94%
- p50
- 833ms
- p99
- 4.46s
- Throughput
- 3.0 tps
- Context
- 128K
- $/Mtok
- $2.50 / $10.00
azure - OpenAI99.98%Healthy24h 99.94%
- p50
- 634ms
- p99
- 5.47s
- Throughput
- 40 tps
- Context
- 128K
- $/Mtok
- $2.50 / $10.00
openai
Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
Availability
Axis starts at 90% so small differences stay visible; it expands to 0 when an endpoint falls below.
Time to first token
Logarithmic axis — the fleet spans two orders of magnitude. p50 and p99 are OpenRouter's rolling 30-minute windows, averaged over the hour.
Throughput
Median tokens per second.